Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2875 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.4688. Min Act: -0.0000

Data Index: 1129851 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.5213. Min Act: -0.0000

Data Index: 454925 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.4154. Min Act: -0.0000

Data Index: 870564 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.3153. Min Act: -0.0001

Data Index: 1141633 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.7626. Min Act: -0.0000

Data Index: 65692 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.0643. Min Act: -0.0000

Data Index: 184086 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.5094. Min Act: -0.0001

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.8764. Min Act: -0.0001

Data Index: 920126 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.1393. Min Act: -0.0000

Data Index: 622272 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.6883. Min Act: -0.0001

Data Index: 669334 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.4279. Min Act: -0.0000

Data Index: 523904 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.0518. Min Act: -0.0000

Data Index: 983697 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.8423. Min Act: -0.0000

Data Index: 1214022 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.9958. Min Act: -0.0000

Data Index: 19826 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.7927. Min Act: -0.0001

Data Index: 755638 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.2399. Min Act: -0.0001

Data Index: 325082 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.5905. Min Act: -0.0000

Data Index: 1149195 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 4.7626. Min Range: -4.7626

Max Act: 4.0817. Min Act: -0.0001

Data Index: 750147 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.8733. Min Act: -0.0000

Data Index: 1358679 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 4.7626. Min Range: -4.7626

Max Act: 3.8531. Min Act: -0.0000

Data Index: 1213587 (C4 (Web Text))

Max Activating Token Index: 298